Perceptual Similarity for Measuring Decision-Making Style and Policy Diversity in Games

TL;DR

This paper enhances an unsupervised perceptual metric for measuring decision-making styles in games, significantly improving accuracy and efficiency across various game genres, and introduces a diversity assessment algorithm.

Contribution

It introduces three key enhancements to the Playstyle Distance metric, boosting measurement accuracy and enabling better analysis of decision-making diversity in games.

Findings

Achieved over 90% accuracy in zero-shot playstyle classification with fewer than 512 observations.

Improved measurement precision through multiscale analysis, perceptual kernels, and intersection-over-union evaluation.

Demonstrated potential of discrete playstyle measures in puzzle and board games.

Abstract

Defining and measuring decision-making styles, also known as playstyles, is crucial in gaming, where these styles reflect a broad spectrum of individuality and diversity. However, finding a universally applicable measure for these styles poses a challenge. Building on Playstyle Distance, the first unsupervised metric to measure playstyle similarity based on game screens and raw actions, we introduce three enhancements to increase accuracy: multiscale analysis with varied state granularity, a perceptual kernel rooted in psychology, and the utilization of the intersection-over-union method for efficient evaluation. These innovations not only advance measurement precision but also offer insights into human cognition of similarity. Across two racing games and seven Atari games, our techniques significantly improve the precision of zero-shot playstyle classification, achieving an accuracy exceeding 90 percent with fewer than 512 observation-action pairs, which is less than half an episode of these games. Furthermore, our experiments with 2048 and Go demonstrate the potential of discrete playstyle measures in puzzle and board games. We also develop an algorithm for assessing decision-making diversity using these measures. Our findings improve the measurement of end-to-end game analysis and the evolution of artificial intelligence for diverse playstyles.